Assessment of Expert-Level Automated Detection of Plasmodium falciparum in Digitized Thin Blood Smear Images.

Importance: Decades of effort have been devoted to establishing an automated microscopic diagnosis of malaria, but there are challenges in achieving expert-level performance in real-world clinical settings because publicly available annotated data for benchmark and validation are required. Objective: To assess an expert-level malaria detection algorithm using a publicly available benchmark image data set. Design, Setting, and Participants: In this diagnostic study, clinically validated malaria image data sets, the Taiwan Images for Malaria Eradication (TIME), were created by digitizing thin blood smears acquired from patients with malaria selected from the biobank of the Taiwan Centers for Disease Control from January 1, 2003, to December 31, 2018. These smear images were annotated by 4 clinical laboratory scientists who worked in medical centers in Taiwan and trained for malaria microscopic diagnosis at the national reference laboratory of the Taiwan Centers for Disease Control. With TIME, a convolutional neural network-based object detection algorithm was developed for identification of malaria-infected red blood cells. A diagnostic challenge using another independent data set within TIME was performed to compare the algorithm performance against that of human experts as clinical validation. Main Outcomes and Measures: Performance on detecting Plasmodium falciparum-infected blood cells was measured by average precision, and performance on detecting P falciparum infection at the image level was measured using sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Results: The TIME data sets contained 8145 images of 36 blood smears from patients with suspected malaria (30 P falciparum-positive and 6 P falciparum-negative smears) that had reliable annotations. For clinical validation, the average precision was 0.885 for detecting P falciparum-infected blood cells and 0.838 for ring form. For detecting P falciparum infection on blood smear images, the algorithm had expert-level performance (sensitivity, 0.995; specificity, 0.900; AUC, 0.997 [95% CI, 0.993-0.999]), especially in detecting ring form (sensitivity, 0.968; specificity, 0.960; AUC, 0.995 [95% CI, 0.990-0.998]) compared with experienced microscopists (mean sensitivity, 0.995 [95% CI, 0.993-0.998]; mean specificity, 0.955 [95% CI, 0.885-1.000]). Conclusions and Relevance: The findings suggest that a clinically validated expert-level malaria detection algorithm can be developed by using reliable data sets.

A rapid and simple determination of protoberberine alkaloids in cortex phellodendri by 1H NMR and its application for quality control of commercial traditional Chinese medicine prescriptions.

Huangbai (cortex Phellodendri, the dried bark of Phellodendron amurense or Phellodendron chinense) is one of the important traditional Chinese medicines. Protoberberine alkaloids were reported to contribute to the biological activity of this species. A highly specific and sensitive method using (1)H NMR has been developed for the quantitative determination of protoberberine alkaloids in Phellodendron species and their commercial traditional Chinese medicine prescriptions. In the region of delta 8.6-8.9, the signals of H-13 of berberine (1) and palmatine (2), were well separated from other signals in methanol-d(4). The quantity of the compounds was calculated by the relative ratio of the integral values of the target peak of each compound to the known amount of internal standard anthracene. This method allows rapid and simple quantization of protoberberine alkaloids from Phellodendron species or the more complex commercial prescriptions in 5 min without any pre-purification steps. The recoveries of berberine and palmatine from P. amurense were in the range of 95-106%. Limit of detection (LOD) and limit of quantitation (LOQ) of them were 1.0 and 1.8 microg/mL, respectively. The advantages of the method were that no reference compounds are required for calibration curves, the quantification could be directly realized on a crude extract, the better selectivity for protoberberine alkaloids and a very significant time-gain could be achieved, in comparison to conventional HPLC methods, for instance.